As deep convolutional neural networks (DNNs) are widely used in various fields of computer vision, leveraging the overfitting ability of the DNN to achieve video resolution upscaling has become a new trend in the modern video delivery system. By dividing videos into chunks and overfitting each chunk with a super-resolution model, the server encodes videos before transmitting them to the clients, thus achieving better video quality and transmission efficiency. However, a large number of chunks are expected to ensure good overfitting quality, which substantially increases the storage and consumes more bandwidth resources for data transmission. On the other hand, decreasing the number of chunks through training optimization techniques usually requires high model capacity, which significantly slows down execution speed. To reconcile such, we propose a novel method for high-quality and efficient video resolution upscaling tasks, which leverages the spatial-temporal information to accurately divide video into chunks, thus keeping the number of chunks as well as the model size to minimum. Additionally, we advance our method into a single overfitting model by a data-aware joint training technique, which further reduces the storage requirement with negligible quality drop. We deploy our models on an off-the-shelf mobile phone, and experimental results show that our method achieves real-time video super-resolution with high video quality. Compared with the state-of-the-art, our method achieves 28 fps streaming speed with 41.6 PSNR, which is 14$\times$ faster and 2.29 dB better in the live video resolution upscaling tasks. Code available in https://github.com/coulsonlee/STDO-CVPR2023.git
EPS: Efficient Patch Sampling for Video Overfitting in Deep Super-Resolution Model Training
Christian Doppler Laboratory ATHENA（Christian Doppler实验室ATHENA）；Alpen-Adria-Universität Klagenfurt（阿尔卑斯-亚德里亚大学克雷格福特）；College of Information and Communication Engineering（信息与通信工程学院）
Deep learning is overwhelmingly dominant in the field of computer vision and image/video processing for the last decade. However, for image and video compression, it lags behind the traditional techniques based on discrete cosine transform (DCT) and linear filters. Built on top of an autoencoder architecture, learned image compression (LIC) systems have drawn enormous attention in recent years. Nevertheless, the proposed LIC systems are still inferior to the state-of-the-art traditional techniques, for example, the Versatile Video Coding (VVC/H.266) standard, due to either their compression pe…
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；The Chinese University of Hong Kong（香港中文大学）
Large deep networks have demonstrated competitive performance in single image super-resolution (SISR), with a huge volume of data involved. However, in real-world scenarios, due to the limited accessible training pairs, large models exhibit undesirable behaviors such as overfitting and memorization. To suppress model overfitting and further enjoy the merits of large model capacity, we thoroughly investigate generic approaches for supplying additional training data pairs. In particular, we introduce a simple learning principle MixUp to train networks on interpolations of sample pairs, which enc…
DroneSR: Rethinking Few-shot Thermal Image Super-Resolution from Drone-based Perspective
School of Information Engineering, Guangdong University of Technology（广东工业大学信息工程学院）；Guangdong Power Grid, Ltd.（广东电网有限公司）；School of Computer Science, Sun Yat-sen University（中山大学计算机学院）
Preventing Overfitting in Deep Image Prior for Hyperspectral Image Denoising
Robotics Institute, Athena Research and Innovation Center（雅典娜研究与创新中心机器人研究所）；School of Electrical and Computer Engineering, National Technical University of Athens（雅典国家技术大学电气与计算机工程学院）
École Polytechnique Fédérale de Lausanne（洛桑联邦理工学院）
We mainly analyze and solve the overfitting problem of deep image prior (DIP). Deep image prior can solve inverse problems such as super-resolution, inpainting and denoising. The main advantage of DIP over other deep learning approaches is that it does not need access to a large dataset. However, due to the large number of parameters of the neural network and noisy data, DIP overfits to the noise in the image as the number of iterations grows. In the thesis, we use hybrid deep image priors to avoid overfitting. The hybrid priors are to combine DIP with an explicit prior such as total variation…
An agent that is capable of predicting what happens next can perform a variety of tasks through planning with no additional training. Furthermore, such an agent can internally represent the complex dynamics of the real-world and therefore can acquire a representation useful for a variety of visual perception tasks. This makes predicting the future frames of a video, conditioned on the observed past and potentially future actions, an interesting task which remains exceptionally challenging despite many recent advances. Existing video prediction models have shown promising results on simple narr…
School of Computer and Communication Sciences, EPFL（洛桑联邦理工学院计算机与通信科学学院）
Super-resolution and denoising are ill-posed yet fundamental image restoration tasks. In blind settings, the degradation kernel or the noise level are unknown. This makes restoration even more challenging, notably for learning-based methods, as they tend to overfit to the degradation seen during training. We present an analysis, in the frequency domain, of degradation-kernel overfitting in super-resolution and introduce a conditional learning perspective that extends to both super-resolution and denoising. Building on our formulation, we propose a stochastic frequency masking of images used in…
Beijing University of Posts and Telecommunications（北京邮电大学）；Intel Labs China（英特尔中国实验室）
Internet video delivery has undergone a tremendous explosion of growth over the past few years. However, the quality of video delivery system greatly depends on the Internet bandwidth. Deep Neural Networks (DNNs) are utilized to improve the quality of video delivery recently. These methods divide a video into chunks, and stream LR video chunks and corresponding content-aware models to the client. The client runs the inference of models to super-resolve the LR chunks. Consequently, a large number of models are streamed in order to deliver a video. In this paper, we first carefully study the rel…
Video compression is a critical component of Internet video delivery. Recent work has shown that deep learning techniques can rival or outperform human-designed algorithms, but these methods are significantly less compute and power-efficient than existing codecs. This paper presents a new approach that augments existing codecs with a small, content-adaptive super-resolution model that significantly boosts video quality. Our method, SRVC, encodes video into two bitstreams: (i) a content stream, produced by compressing downsampled low-resolution video with the existing codec, (ii) a model stream…
Nanjing University of Science and Technology（南京理工大学）
Existing deep learning-based video super-resolution (SR) methods usually depend on the supervised learning approach, where the training data is usually generated by the blurring operation with known or predefined kernels (e.g., Bicubic kernel) followed by a decimation operation. However, this does not hold for real applications as the degradation process is complex and cannot be approximated by these idea cases well. Moreover, obtaining high-resolution (HR) videos and the corresponding low-resolution (LR) ones in real-world scenarios is difficult. To overcome these problems, we propose a self-…
We propose the first reference-based video super-resolution (RefVSR) approach that utilizes reference videos for high-fidelity results. We focus on RefVSR in a triple-camera setting, where we aim at super-resolving a low-resolution ultra-wide video utilizing wide-angle and telephoto videos. We introduce the first RefVSR network that recurrently aligns and propagates temporal reference features fused with features extracted from low-resolution frames. To facilitate the fusion and propagation of temporal reference features, we propose a propagative temporal fusion module. For learning and evalua…
Wuhan University（武汉大学）；Hubei University of Economics（湖北经济学院）；Central China Normal University（华中师范大学）；Arizona State University（亚利桑那州立大学）；State University of New York at Buffalo（纽约州立大学布法罗分校）
Video super-resolution is currently one of the most active research topics in computer vision as it plays an important role in many visual applications. Generally, video super-resolution contains a significant component, i.e., motion compensation, which is used to estimate the displacement between successive video frames for temporal alignment. Optical flow, which can supply dense and sub-pixel motion between consecutive frames, is among the most common ways for this task. To obtain a good understanding of the effect that optical flow acts in video super-resolution, in this work, we conduct a …
Recently, image super-resolution has been widely studied and achieved significant progress by leveraging the power of deep convolutional neural networks. However, there has been limited advancement in video super-resolution (VSR) due to the complex temporal patterns in videos. In this paper, we investigate how to adapt state-of-the-art methods of image super-resolution for video super-resolution. The proposed adapting method is straightforward. The information among successive frames is well exploited, while the overhead on the original image super-resolution method is negligible. Furthermore,…
Southeast University（东南大学）；University of Cambridge（剑桥大学）
Face video super-resolution algorithm aims to reconstruct realistic face details through continuous input video sequences. However, existing video processing algorithms usually contain redundant parameters to guarantee different super-resolution scenes. In this work, we focus on super-resolution of face areas in original video scenes, while rest areas are interpolated. This specific super-resolved task makes it possible to cut redundant parameters in general video super-resolution networks. We construct a dataset consisting entirely of face video sequences for network training and evaluation, …
State-of-the-art video action classifiers often suffer from overfitting. They tend to be biased towards specific objects and scene cues, rather than the foreground action content, leading to sub-optimal generalization performances. Recent data augmentation strategies have been reported to address the overfitting problems in static image classifiers. Despite the effectiveness on the static image classifiers, data augmentation has rarely been studied for videos. For the first time in the field, we systematically analyze the efficacy of various data augmentation strategies on the video classifica…
Low-Cost Test-Time Adaptation for Robust Video Editing
UESTC（电子科技大学）；USTC（中国科学技术大学）；University of Minnesota–Twin Cities（明尼苏达大学-双城分校）；Emory University（埃默里大学）；Nanjing University（南京大学）；Lanzhou University（兰州大学）；Ohio State University, Columbus（俄亥俄州立大学-哥伦布分校）；Chinese Academy of Sciences（中国科学院）；Peking University（北京大学）
School of Computer Science and Engineering, Southeast University, Nanjing, China（计算机科学与工程学院，东南大学，南京，中国）；Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, China（新一代人工智能技术及其跨学科应用关键实验室（东南大学），教育部，中国）
针对多模态视频模型中强模态主导导致的过拟合与模态不平衡问题，提出 MM 及改进的 B-MM 方法，通过动态调整模态混合比例提升泛化能力与鲁棒性。
Semantic video segmentation is a key challenge for various applications. This paper presents a new model named Noisy-LSTM, which is trainable in an end-to-end manner, with convolutional LSTMs (ConvLSTMs) to leverage the temporal coherency in video frames. We also present a simple yet effective training strategy, which replaces a frame in video sequence with noises. This strategy spoils the temporal coherency in video frames during training and thus makes the temporal links in ConvLSTMs unreliable, which may consequently improve feature extraction from video frames, as well as serve as a regula…
Supervised training of neural networks requires large, diverse and well annotated data sets. In the medical field, this is often difficult to achieve due to constraints in time, expert knowledge and prevalence of an event. Artificial data augmentation can help to prevent overfitting and improve the detection of rare events as well as overall performance. However, most augmentation techniques use purely spatial transformations, which are not sufficient for video data with temporal correlations. In this paper, we present a novel methodology for workflow augmentation and demonstrate its benefit f…
University of North Carolina at Charlotte（北卡罗来纳大学夏洛特分校）
In this paper, we present and discuss a deep mixture model with online knowledge distillation (MOD) for large-scale video temporal concept localization, which is ranked 3rd in the 3rd YouTube-8M Video Understanding Challenge. Specifically, we find that by enabling knowledge sharing with online distillation, fintuning a mixture model on a smaller dataset can achieve better evaluation performance. Based on this observation, in our final solution, we trained and fintuned 12 NeXtVLAD models in parallel with a 2-layer online distillation structure. The experimental results show that the proposed di…
We tackle the problem of predicting saliency maps for videos of dynamic scenes. We note that the accuracy of the maps reconstructed from the gaze data of a fixed number of observers varies with the frame, as it depends on the content of the scene. This issue is particularly pressing when a limited number of observers are available. In such cases, directly minimizing the discrepancy between the predicted and measured saliency maps, as traditional deep-learning methods do, results in overfitting to the noisy data. We propose a noise-aware training (NAT) paradigm that quantifies and accounts for …
Tsinghua University（清华大学）；Tencent Media Lab（腾讯媒体实验室）；Research Institute of Tsinghua University in Shenzhen（清华大学深圳研究院）
Denoisers trained with synthetic data often fail to cope with the diversity of unknown noises, giving way to methods that can adapt to existing noise without knowing its ground truth. Previous image-based method leads to noise overfitting if directly applied to video denoisers, and has inadequate temporal information management especially in terms of occlusion and lighting variation, which considerably hinders its denoising performance. In this paper, we propose a general framework for video denoising networks that successfully addresses these challenges. A novel twin sampler assembles trainin…
On the Generalization and Causal Explanation in Self-Supervised Learning
Institute of Software Chinese Academy of Sciences（中国科学院软件研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Tsinghua University（清华大学）；Hong Kong University of Science and Technology（香港科技大学）
For many years, the emotion recognition task has remained one of the most interesting and important problems in the field of human-computer interaction. In this study, we consider the emotion recognition task as a classification as well as a regression task by processing encoded emotions in different datasets using deep learning models. Our model combines convolutional neural network (CNN) with recurrent neural network (RNN) to predict dimensional emotions on video data. At the first step, CNN extracts feature vectors from video frames. In the second step, we fed these feature vectors to train…
An empirical study of the effect of video encoders on Temporal Video Grounding
Department of Computer Science, University of Chile（计算机科学系，智利大学）；CENIA and IMFD（CENIA和IMFD）；Australian Institute for Machine Learning, University of Adelaide（澳大利亚机器学习研究所，阿德莱德大学）；National Institute of Advanced Industrial Science and Technology（国家先进工业科学与技术研究所）
Beijing Institute of Technology（北京理工大学）；University of East Anglia（东安格利亚大学）
This paper proposes a deep learning model to efficiently detect salient regions in videos. It addresses two important issues: (1) deep video saliency model training with the absence of sufficiently large and pixel-wise annotated video data, and (2) fast video saliency training and detection. The proposed deep video saliency network consists of two modules, for capturing the spatial and temporal saliency information, respectively. The dynamic saliency model, explicitly incorporating saliency estimates from the static saliency model, directly produces spatiotemporal saliency inference without ti…
Video captioning is an advanced multi-modal task which aims to describe a video clip using a natural language sentence. The encoder-decoder framework is the most popular paradigm for this task in recent years. However, there exist some problems in the decoder of a video captioning model. We make a thorough investigation into the decoder and adopt three techniques to improve the performance of the model. First of all, a combination of variational dropout and layer normalization is embedded into a recurrent unit to alleviate the problem of overfitting. Secondly, a new online method is proposed t…
Unconstrained video recognition and Deep Convolution Network (DCN) are two active topics in computer vision recently. In this work, we apply DCNs as frame-based recognizers for video recognition. Our preliminary studies, however, show that video corpora with complete ground truth are usually not large and diverse enough to learn a robust model. The networks trained directly on the video data set suffer from significant overfitting and have poor recognition rate on the test set. The same lack-of-training-sample problem limits the usage of deep models on a wide range of computer vision problems …
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；Shenzhen Institute of Artificial Intelligence and Robotics for Society（深圳人工智能与机器人研究院）
Temporal convolution has been widely used for video classification. However, it is performed on spatio-temporal contexts in a limited view, which often weakens its capacity of learning video representation. To alleviate this problem, we propose a concise and novel SmallBig network, with the cooperation of small and big views. For the current time step, the small view branch is used to learn the core semantics, while the big view branch is used to capture the contextual semantics. Unlike traditional temporal convolution, the big view branch can provide the small view branch with the most activa…
University of Electronic Science and Technology of China（电子科技大学）；Tsinghua University（清华大学）；Sichuan University（四川大学）；University of Florida（佛罗里达大学）
Noisy labels composed of correct and corrupted ones are pervasive in practice. They might significantly deteriorate the performance of convolutional neural networks (CNNs), because CNNs are easily overfitted on corrupted labels. To address this issue, inspired by an observation, deep neural networks might first memorize the probably correct-label data and then corrupt-label samples, we propose a novel yet simple self-paced resistance framework to resist corrupted labels, without using any clean validation data. The proposed framework first utilizes the memorization effect of CNNs to learn a cu…
Vulnerability-Aware Spatio-Temporal Learning for Generalizable Deepfake Video Detection
CVI 2 , SnT, University of Luxembourg（CVI 2 ，SnT，卢森堡大学）；Cristal Laboratory, National School of Computer Sciences, University of Manouba（Cristal实验室，国家计算机科学学校，曼努巴大学）
VideoPure: Diffusion-based Adversarial Purification for Video Recognition
Shanghai Engineering Research Center of AI Robotics, Academy for Engineering & Technology, Fudan University（复旦大学工程与技术学院上海市人工智能机器人工程研究中心）；Engineering Research Center of AI & Robotics, Ministry of Education, Academy for Engineering & Technology, Fudan University（复旦大学工程与技术学院教育部人工智能与机器人工程研究中心）；School of Computer Science, Fudan University（复旦大学计算机科学学院）
Few-Shot Learning in Video and 3D Object Detection: A Survey
Canizaro Livingston Gulf States Center for Environmental Informatics（卡尼扎罗利文斯顿湾州环境信息中心）；University of New Orleans（新奥尔良大学）；US Army Corps of Engineers（美国陆军工程兵团）；Center for Geospatial Sciences, Naval Research Laboratory（海军研究实验室地理空间科学中心）
University of Oulu（奥卢大学）；University of Oxford（牛津大学）；Xi’an Jiaotong University（西安交通大学）；The University of Hong Kong（香港大学）
Remote photoplethysmography (rPPG), which aims at measuring heart activities and physiological signals from facial video without any contact, has great potential in many applications (e.g., remote healthcare and affective computing). Recent deep learning approaches focus on mining subtle rPPG clues using convolutional neural networks with limited spatio-temporal receptive fields, which neglect the long-range spatio-temporal perception and interaction for rPPG modeling. In this paper, we propose the PhysFormer, an end-to-end video transformer based architecture, to adaptively aggregate both loc…
BridgeV2W: Bridging Video Generation Models to Embodied World Models via Embodiment Masks
New Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences（模式识别新实验室（NLPR），自动化研究所，中国科学院）；School of Artificial Intelligence, University of Chinese Academy of Sciences（人工智能学院，中国科学院大学）；Shandong University（山东大学）
Learning Natural Consistency Representation for Face Forgery Video Detection
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Tsinghua University（清华大学）；RealAI
High-Quality Proposal Encoding and Cascade Denoising for Imaginary Supervised Object Detection
Institute of Cyberspace Security, Harbin Institute of Technology, Shenzhen（网络安全研究所，哈尔滨工业大学，深圳）；Department of New Networks, Peng Cheng Laboratory（新网络部门，鹏城实验室）；School of Cyberspace Science, Harbin Institute of Technology（空间科学学院，哈尔滨工业大学）；Center on Machine Learning Research, Harbin Institute of Technology（机器学习研究中心，哈尔滨工业大学）；Faculty of Information Technology, Monash University（信息技术学院，墨尔本大学）
Ball trajectory data are one of the most fundamental and useful information in the evaluation of players' performance and analysis of game strategies. Although vision-based object tracking techniques have been developed to analyze sport competition videos, it is still challenging to recognize and position a high-speed and tiny ball accurately. In this paper, we develop a deep learning network, called TrackNet, to track the tennis ball from broadcast videos in which the ball images are small, blurry, and sometimes with afterimage tracks or even invisible. The proposed heatmap-based deep learnin…
